{"id":"https://openalex.org/W1977655452","doi":"https://doi.org/10.1177/0278364913495721","title":"Reinforcement learning in robotics: A survey","display_name":"Reinforcement learning in robotics: A survey","publication_year":2013,"publication_date":"2013-08-23","ids":{"openalex":"https://openalex.org/W1977655452","doi":"https://doi.org/10.1177/0278364913495721","mag":"1977655452"},"language":"en","primary_location":{"id":"doi:10.1177/0278364913495721","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364913495721","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Reinforcement_Learning_in_Robotics_A_Survey/6560648","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035229829","display_name":"Jens Kober","orcid":"https://orcid.org/0000-0001-7257-5434"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]},{"id":"https://openalex.org/I4210112253","display_name":"Honda (Germany)","ror":"https://ror.org/022c1xk47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210112253"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jens Kober","raw_affiliation_strings":["Bielefeld University, CoR-Lab Research Institute for Cognition and Robotics, Bielefeld, Germany","Honda Research Institute Europe, Offenbach/Main, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bielefeld University, CoR-Lab Research Institute for Cognition and Robotics, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"Honda Research Institute Europe, Offenbach/Main, Germany","institution_ids":["https://openalex.org/I4210112253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112411386","display_name":"J. Andrew Bagnell","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Andrew Bagnell","raw_affiliation_strings":["Carnegie Mellon University, Robotics Institute, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Robotics Institute, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems, Department of Empirical Inference, T\u00fcbingen, Germany","Technische Universit\u00e4t Darmstadt, FB Informatik, FG Intelligent Autonomous Systems, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, Department of Empirical Inference, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, FB Informatik, FG Intelligent Autonomous Systems, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035229829"],"corresponding_institution_ids":["https://openalex.org/I20121455","https://openalex.org/I4210112253"],"apc_list":null,"apc_paid":null,"fwci":127.9986,"has_fulltext":false,"cited_by_count":3034,"citation_normalized_percentile":{"value":0.99981178,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"32","issue":"11","first_page":"1238","last_page":"1274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.934499979019165,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9021483659744263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7241173982620239},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6924638748168945},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5696312785148621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5615630149841309},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5554027557373047},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5465070009231567},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4699055552482605},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44813403487205505},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.42768731713294983},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3826441764831543},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.321158230304718},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22845321893692017},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1455981433391571},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13350287079811096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9021483659744263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7241173982620239},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6924638748168945},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5696312785148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5615630149841309},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5554027557373047},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5465070009231567},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4699055552482605},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44813403487205505},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.42768731713294983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3826441764831543},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.321158230304718},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22845321893692017},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1455981433391571},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13350287079811096},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.1177/0278364913495721","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364913495721","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},{"id":"pmh:oai:repository.cmu.edu:robotics-2134","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=2134&context=robotics","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics Institute","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.366.5647","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.366.5647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ri.cmu.edu/pub_files/2013/7/Kober_IJRR_2013.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.2948","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.2948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ias.tu-darmstadt.de/uploads/Publications/Kober_IJRR_2013.pdf","raw_type":"text"},{"id":"pmh:oai:escidoc.org:escidoc:1945291","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0017-8A7E-8","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:figshare.com:article/6560648","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Reinforcement_Learning_in_Robotics_A_Survey/6560648","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pub.librecat.org:2636036","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2636036","pdf_url":null,"source":{"id":"https://openalex.org/S4306401671","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kober J, Bagnell JA, Peters J. Reinforcement learning in robotics: A survey. <em>The International Journal Of Robotics Research</em>. 2013;32(11):1238-1274.","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.mpg.de:item_1746982","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000E-FE69-2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Adaption, Learning, and Optimization","raw_type":"info:eu-repo/semantics/bookPart"},{"id":"doi:10.1184/r1/6560648.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6560648.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6560648","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Reinforcement_Learning_in_Robotics_A_Survey/6560648","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":262,"referenced_works":["https://openalex.org/W49905056","https://openalex.org/W59183349","https://openalex.org/W59256581","https://openalex.org/W60181528","https://openalex.org/W79460984","https://openalex.org/W107583932","https://openalex.org/W155952036","https://openalex.org/W164706946","https://openalex.org/W174941419","https://openalex.org/W203276351","https://openalex.org/W304821478","https://openalex.org/W391985582","https://openalex.org/W398859631","https://openalex.org/W620914500","https://openalex.org/W658381347","https://openalex.org/W995630646","https://openalex.org/W1130790960","https://openalex.org/W1435458549","https://openalex.org/W1481659984","https://openalex.org/W1483202606","https://openalex.org/W1491843047","https://openalex.org/W1499408472","https://openalex.org/W1499669280","https://openalex.org/W1500910471","https://openalex.org/W1506176787","https://openalex.org/W1506806321","https://openalex.org/W1506832649","https://openalex.org/W1507591516","https://openalex.org/W1509504119","https://openalex.org/W1511864092","https://openalex.org/W1515851193","https://openalex.org/W1516418405","https://openalex.org/W1516801383","https://openalex.org/W1517733364","https://openalex.org/W1520096009","https://openalex.org/W1520379281","https://openalex.org/W1520597402","https://openalex.org/W1525280637","https://openalex.org/W1534355532","https://openalex.org/W1540685400","https://openalex.org/W1543217731","https://openalex.org/W1545763673","https://openalex.org/W1549353711","https://openalex.org/W1563483395","https://openalex.org/W1564755532","https://openalex.org/W1571179961","https://openalex.org/W1573316549","https://openalex.org/W1575592356","https://openalex.org/W1580887022","https://openalex.org/W1583116672","https://openalex.org/W1588998206","https://openalex.org/W1592847719","https://openalex.org/W1596805757","https://openalex.org/W1597173708","https://openalex.org/W1599132676","https://openalex.org/W1599610710","https://openalex.org/W1609959227","https://openalex.org/W1626155273","https://openalex.org/W1663973292","https://openalex.org/W1746819321","https://openalex.org/W1751034982","https://openalex.org/W1752122489","https://openalex.org/W1755933627","https://openalex.org/W1777239053","https://openalex.org/W1851793550","https://openalex.org/W1876639556","https://openalex.org/W1931792391","https://openalex.org/W1949804828","https://openalex.org/W1949974402","https://openalex.org/W1963873191","https://openalex.org/W1964271816","https://openalex.org/W1964710473","https://openalex.org/W1967499360","https://openalex.org/W1970916399","https://openalex.org/W1975318316","https://openalex.org/W1979071892","https://openalex.org/W1985161922","https://openalex.org/W1985249384","https://openalex.org/W1986014385","https://openalex.org/W1986808060","https://openalex.org/W1988071341","https://openalex.org/W1994923984","https://openalex.org/W1999874108","https://openalex.org/W2006036383","https://openalex.org/W2007407491","https://openalex.org/W2012204020","https://openalex.org/W2012392077","https://openalex.org/W2016482167","https://openalex.org/W2017995647","https://openalex.org/W2018346149","https://openalex.org/W2021004298","https://openalex.org/W2021128738","https://openalex.org/W2025752438","https://openalex.org/W2026659355","https://openalex.org/W2026667632","https://openalex.org/W2031571562","https://openalex.org/W2033180067","https://openalex.org/W2035384032","https://openalex.org/W2035808435","https://openalex.org/W2037199950","https://openalex.org/W2041812416","https://openalex.org/W2042322703","https://openalex.org/W2042882799","https://openalex.org/W2048226872","https://openalex.org/W2051620263","https://openalex.org/W2063591749","https://openalex.org/W2064765703","https://openalex.org/W2070678636","https://openalex.org/W2070797946","https://openalex.org/W2073995413","https://openalex.org/W2080039641","https://openalex.org/W2082764616","https://openalex.org/W2096001037","https://openalex.org/W2097803672","https://openalex.org/W2098432798","https://openalex.org/W2098524868","https://openalex.org/W2098774185","https://openalex.org/W2100235553","https://openalex.org/W2100538121","https://openalex.org/W2103285838","https://openalex.org/W2103787878","https://openalex.org/W2105038027","https://openalex.org/W2105546430","https://openalex.org/W2105947986","https://openalex.org/W2106261932","https://openalex.org/W2106432400","https://openalex.org/W2107726111","https://openalex.org/W2108302062","https://openalex.org/W2108579172","https://openalex.org/W2108682071","https://openalex.org/W2108734173","https://openalex.org/W2109008048","https://openalex.org/W2109158177","https://openalex.org/W2109572794","https://openalex.org/W2110029398","https://openalex.org/W2110771465","https://openalex.org/W2112264645","https://openalex.org/W2113048001","https://openalex.org/W2115138863","https://openalex.org/W2115450028","https://openalex.org/W2115955688","https://openalex.org/W2118459920","https://openalex.org/W2118637732","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2120070743","https://openalex.org/W2123327324","https://openalex.org/W2123663688","https://openalex.org/W2123967136","https://openalex.org/W2125074935","https://openalex.org/W2125612430","https://openalex.org/W2126105931","https://openalex.org/W2126149578","https://openalex.org/W2127036288","https://openalex.org/W2127412976","https://openalex.org/W2127572219","https://openalex.org/W2127908581","https://openalex.org/W2129515556","https://openalex.org/W2130105540","https://openalex.org/W2132400125","https://openalex.org/W2132602063","https://openalex.org/W2133932631","https://openalex.org/W2135376858","https://openalex.org/W2139053308","https://openalex.org/W2139418546","https://openalex.org/W2139769245","https://openalex.org/W2140135625","https://openalex.org/W2140219596","https://openalex.org/W2142828048","https://openalex.org/W2143007722","https://openalex.org/W2146151428","https://openalex.org/W2146396918","https://openalex.org/W2148112459","https://openalex.org/W2149192758","https://openalex.org/W2150818585","https://openalex.org/W2151237105","https://openalex.org/W2151250975","https://openalex.org/W2151975555","https://openalex.org/W2152166054","https://openalex.org/W2152827112","https://openalex.org/W2152951714","https://openalex.org/W2154760503","https://openalex.org/W2155027007","https://openalex.org/W2155723829","https://openalex.org/W2155921514","https://openalex.org/W2156377376","https://openalex.org/W2157720571","https://openalex.org/W2158349948","https://openalex.org/W2158485545","https://openalex.org/W2158796564","https://openalex.org/W2159298583","https://openalex.org/W2161872510","https://openalex.org/W2162621328","https://openalex.org/W2162717641","https://openalex.org/W2163387410","https://openalex.org/W2163533082","https://openalex.org/W2163602945","https://openalex.org/W2164032318","https://openalex.org/W2164479831","https://openalex.org/W2165131254","https://openalex.org/W2165421048","https://openalex.org/W2166302491","https://openalex.org/W2167647761","https://openalex.org/W2168921921","https://openalex.org/W2168945912","https://openalex.org/W2169209873","https://openalex.org/W2169498096","https://openalex.org/W2170164558","https://openalex.org/W2172141376","https://openalex.org/W2172158418","https://openalex.org/W2172968643","https://openalex.org/W2198041288","https://openalex.org/W2292999476","https://openalex.org/W2294729144","https://openalex.org/W2331739408","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2399574992","https://openalex.org/W2489467106","https://openalex.org/W2489939061","https://openalex.org/W2544683879","https://openalex.org/W2549684528","https://openalex.org/W2577236900","https://openalex.org/W2591436094","https://openalex.org/W2595840341","https://openalex.org/W2596356468","https://openalex.org/W2600687292","https://openalex.org/W2602256192","https://openalex.org/W2606098075","https://openalex.org/W2608909910","https://openalex.org/W2610184409","https://openalex.org/W2610686804","https://openalex.org/W2613433911","https://openalex.org/W2623785075","https://openalex.org/W2725122918","https://openalex.org/W2752899502","https://openalex.org/W2767787240","https://openalex.org/W2798766386","https://openalex.org/W2799700442","https://openalex.org/W2904250082","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W2962957031","https://openalex.org/W2964349150","https://openalex.org/W2978329087","https://openalex.org/W3022423118","https://openalex.org/W3143334844","https://openalex.org/W3144155561","https://openalex.org/W3207782042","https://openalex.org/W4206567137","https://openalex.org/W4210473396","https://openalex.org/W4229554368","https://openalex.org/W4233061323","https://openalex.org/W4235424703","https://openalex.org/W4243489454","https://openalex.org/W4245108548","https://openalex.org/W4248373316","https://openalex.org/W4249441547","https://openalex.org/W4253187718","https://openalex.org/W4285719527","https://openalex.org/W4301630257","https://openalex.org/W4396738453"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,74,88,155],"offers":[2],"to":[3,43,46,57],"robotics":[4],"a":[5,68,119,121,145],"framework":[6],"and":[7,16,29,50,104,111,133,140,161,167],"set":[8],"of":[9,14,22,70,101,108,124],"tools":[10],"for":[11,31,75,171],"the":[12,20,59,62,99,102,106,129,168],"design":[13],"sophisticated":[15],"hard-to-engineer":[17],"behaviors.":[18],"Conversely,":[19],"challenges":[21,84],"robotic":[23],"problems":[24],"provide":[25],"both":[26,82],"inspiration,":[27],"impact,":[28],"validation":[30],"developments":[32],"in":[33,72,78,85,114,148],"reinforcement":[34,73,87,154],"learning.":[35],"The":[36],"relationship":[37],"between":[38,48,61,131,138],"disciplines":[39],"has":[40],"sufficient":[41],"promise":[42],"be":[44,158],"likened":[45],"that":[47],"physics":[49],"mathematics.":[51],"In":[52],"this":[53],"article,":[54],"we":[55,151,162],"attempt":[56],"strengthen":[58],"links":[60],"two":[63],"research":[64],"communities":[65],"by":[66],"providing":[67],"survey":[69],"work":[71],"behavior":[76],"generation":[77],"robots.":[79],"We":[80,94],"highlight":[81],"key":[83],"robot":[86],"as":[89,91,135,137],"well":[90,136],"notable":[92],"successes.":[93,117],"discuss":[95],"how":[96,153],"contributions":[97],"tamed":[98],"complexity":[100],"domain":[103],"study":[105],"role":[107],"algorithms,":[109],"representations,":[110],"prior":[112],"knowledge":[113],"achieving":[115],"these":[116],"As":[118],"result,":[120],"particular":[122],"focus":[123],"our":[125],"paper":[126],"lies":[127],"on":[128],"choice":[130],"model-based":[132],"model-free":[134],"value-function-based":[139],"policy-search":[141],"methods.":[142],"By":[143],"analyzing":[144],"simple":[146],"problem":[147],"some":[149],"detail":[150],"demonstrate":[152],"approaches":[156],"may":[157],"profitably":[159],"applied,":[160],"note":[163],"throughout":[164],"open":[165],"questions":[166],"tremendous":[169],"potential":[170],"future":[172],"research.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":68},{"year":2025,"cited_by_count":313},{"year":2024,"cited_by_count":313},{"year":2023,"cited_by_count":308},{"year":2022,"cited_by_count":294},{"year":2021,"cited_by_count":448},{"year":2020,"cited_by_count":372},{"year":2019,"cited_by_count":301},{"year":2018,"cited_by_count":202},{"year":2017,"cited_by_count":152},{"year":2016,"cited_by_count":122},{"year":2015,"cited_by_count":77},{"year":2014,"cited_by_count":47},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}